Webly Supervised Learning Meets Zero-shot Learning: A Hybrid Approach for Fine-Grained Classification

By Li Niu, Ashok Narayanan Veeraraghavan, Ashutosh Sabharwal. 2018

71 citations recorded by the source corpus.

Fine-grained image classification, which targets at distinguishing subtle distinctions among various subordinate categories, remains a very difficult task due to the high annotation cost of enormous fine-grained categories. To cope with the scarcity of well-labeled training images, existing works mainly follow two research directions: 1) utilize freely available web images without human annotation; 2) only annotate some fine-grained categories and transfer the knowledge to other fine-grained categories, which falls into the scope of zero-shot learning (ZSL). However, the above two directions have their own drawbacks. For the first direction, the labels of web images are very noisy and the data distribution between web images and test images are considerably different. For the second direction, the performance gap between ZSL and traditional supervised learning is still very large. The drawbacks of the above two directions motivate us to design a new framework which can jointly leverage both web data and auxiliary labeled categories to predict the test categories that are not associated with any well-labeled training images. Comprehensive experiments on three benchmark datasets demonstrate the effectiveness of our proposed framework.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Aniruddha Kembhavi
2. Pietro Zanuttigh
3. Umberto Michieli
4. Christopher Clark
5. Marco Toldo
6. Andrea Maracani
7. Zongben Xu
8. Mohit Bansal

In Computer Vision and Pattern Recognition

1. Aniruddha Kembhavi
2. Pietro Zanuttigh
3. Umberto Michieli
4. Luc Van Gool
5. Chen Change Loy
6. Ming-Hsuan Yang
7. Deyu Meng
8. Christopher Clark

In Radiology, Nuclear Medicine and Imaging

1. Jun Shu
2. Deyu Meng
3. Zongben Xu
4. Li Niu
5. Chunyan Miao
6. Pietro Zanuttigh
7. Han Yu
8. Wei Wang

Citations in the corpus

• RECALL: Replay-based Continual Learning in Semantic Segmentation (2021, background): “Webly-Supervised Learning is an emerging paradigm in which large amounts of web data is exploited for learning CNNs [8, 10, 32].”
• Context-aware Feature Generation For Zero-shot Semantic Segmentation (2020, methodology): “Many ZSL methods [1, 8, 9, 11, 27, 32, 33, 37, 46] attempted to learn a mapping between feature space and semantic embedding space.”
• Small Sample Learning in Big Data Era (2018, methodology): “For example, Niu et al. (2018) recently designed a new framework, which can jointly leverage both web data and auxiliary labeled categories (zero-shot learning) for fine-grained image classification.”
• Webly Supervised Concept Expansion for General Purpose Vision Models (2022, methodology): “As web results improved, works used this data to build object detectors [15,11,46,70,53,82], attribute detectors [21], image taggers [80], large vocabulary categorization models [84,56,24] and fine-grained recognition models [39,57], segmentation models [69,33,72], online dataset builders [44], visu”
• A Survey of Zero-Shot Learning (2019, background): “For example, in [109], zero-shot learning is combined with Webly supervised learning to classify classes that just have noisy labeled images obtained from the web.”